Conversational search plays a vital role in conversational information seeking. As queries seeking dialogues are ambiguous for traditional ad hoc retrieval (IR) systems due to the coreference and omission resolution problems inherent natural language dialogue, resolving these ambiguities is crucial. In this article, we tackle passage retrieval, an important component of search, by addressing qu...

This paper presents the results of the University at Buffalo (UB) in TREC genomics. For this task we used the SMART retrieval system and a pre retrieval expansion method that uses the ABGene and MetaMap tools. We tried two different weighting schemes one using pivoted length normalization (Lnu.ltu) and another using augmented tf-idf (atn.ann). The results show that performance of pivoted length...

OBJECTIVE Identify the set of features that best explained the variation in the performance measure of TREC 2006 Genomics information extraction task, Mean Average Passage Precision (MAPP). METHODS A multivariate regression model was built using a backward-elimination approach as a function of certain generalized features that were common to all the algorithms used by TREC 2006 Genomics track...

Speech interfaces and dialogue processing abilities have promise for improving the utility of open-domain question answering (QA). We propose a novel method of resolving disambiguation problems arisen in those speech and dialogue enhanced QA tasks. The proposed method exploits passage retrieval, which is one of main components common in many QA systems. The basic idea of the method is that the ...

Testing previously studied information enhances long-term memory, particularly when the information is successfully retrieved from memory. The authors examined the effect of unsuccessful retrieval attempts on learning. Participants in 5 experiments read an essay about vision. In the test condition, they were asked about embedded concepts before reading the passage; in the extended study conditi...

The Oregon Health & Science University submission to the TREC 2007 Genomics Track approached the entity list question answering task using a modular object oriented system framework. A system object coordinates a collection of processing objects into a pipe that constructs a set of queries, retrieves passage, and then processes those passages into a final output answer set. Using the framework ...

We present the passage reranking component of a general literature navigation system. Based on weighted keyword scoring without automatic enhancements such as term expansion, the system performed slightly above average on all three tasks, with a strong performance on aspect retrieval.

We propose a framework for discriminative IR atop linguistic features, trained to improve the recall of answer candidate passage retrieval, the initial step in text-based question answering. We formalize this as an instance of linear feature-based IR, demonstrating a 34% 43% improvement in recall for candidate triage for QA.

In this paper we explore the application of fuzzy logic and data fusion techniques to improve the performance of passage retrieval in open domain Question Answering Systems (QAS). Our experiments show that our proposed mechanisms provide significant performance improvements when compared to other similar systems.